I've moved: I now work at Synthesized (https://www.synthesized.io). Further updates to follow.
I am a postdoctoral researcher in statistics at the University of Cambridge, working on the mathematics of deep learning. Previously I worked as a Fondation Mathématique Jacques Hadamard postdoctoral fellow at the Département de Mathématiques d'Orsay, at Université Paris-Saclay. My PhD was in the Statistical Laboratory of the University of Cambridge, supervised by Richard Nickl. My research interests include theoretical guarantees for machine learning, frequentist validity of Bayesian procedures, false discovery rates, and hidden Markov models.
I have a blog where I (infrequently) attempt to explain simply some bits of maths that have caught my interest.
2011-2015 BA with MMath, University of Cambridge. My Part III essay, supervised by Richard Nickl and Jakob Söhl was on Nonparametric Drift Estimation from Low-Frequency Data.
2015-2019 PhD student in statistical theory, University of Cambridge.
2019-2021 Postdoc at Université Paris-Sud, working in particular with Elisabeth Gassiat, and with Ismael Castillo (at Sorbonne Université).
[9] Deep Gaussian Process Priors for Bayesian Inference in Nonlinear Inverse Problems, with Neil Deo, 2023 preprint.
[8] Frontiers to the learning of nonparametric hidden Markov models, with Elisabeth Gassiat and Zacharie Naulet, 2023 preprint.
[7] Sharp multiple testing boundary for sparse sequences, with Ismael Castillo and Etienne Roquain, 2023 preprint.
[6] Fundamental limits for learning hidden Markov model parameters, with Elisabeth Gassiat and Zacharie Naulet. IEEE 2022.
[5] Empirical Bayes cumulative l–value multiple testing procedure for sparse sequences, with Ismael Castillo and Etienne Roquain. EJS 2022.
[4] Multiple testing in nonparametric hidden Markov models: An empirical Bayes approach, with Ismael Castillo and Elisabeth Gassiat, JMLR 2022.
[3] Consistency of nonparametric Bayesian methods for two statistical inverse problems arising from partial differential equations. 2020 PhD thesis
[2] On statistical Calderón problems, with Richard Nickl. Mathematical Statistics and Learning, 2019 (arxiv version is the same as the published version up to typographical changes and references [31] and [32] changing order).
[1] Nonparametric Bayesian posterior contraction rates for scalar diffusions with high-frequency data. Bernoulli, 2019.
ANR BASICS workshop 29-30th September 2022. Slides
MHC2021 (hybrid conference), 2-4th June 2021. Poster
Young Data Science Researcher Seminar Zurich (online seminar), 11th December 2020. Slides
ANR BASICS group meeting. Slides
Mathematical and Statistical Challenges in Uncertainty Quantification (online conference), 13-16th July 2020. Slides
Séminaire Parisien de Statistique, 17th February 2020. Slides (omitted: the blackboard portion of the talk)
BNP12, Oxford, 24-28th June 2019. Poster
Statistics conference in honor of Aad van der Vaart's 60th birthday, 17-21st June 2019. Poster
Séminaire de Statistique, LPSM Paris, 12th February 2019. Slides
Young Researchers' Meeting in Mathematical Statistics, LPSM Paris, 24-26th September, 2018. Slides
ISBA World Meeting, Edinburgh, 24-29th June 2018. Video and slides
Uncertainty Quantification in Complex, Nonparametric Statistical Models, Lorentz Centre, 16-20th April 2018. Introductory slides and poster
Uncertainty Quantification for inverse problems in complex systems 9-13th April. Poster
Mannheim Probability and Statistics Seminar, 22nd November 2017. Slides
I have given supervisions and examples classes in the following courses.
1st year courses: Vectors and Matrices, Analysis I, Numbers and Sets, Groups, Probability2nd year courses: Metric and Topological Spaces, Analysis and Topology, Statistics3rd year courses: Linear Analysis, Applied Probability, Principles of Statistics, Mathematics of Machine LearningPart III: Gaussian Processes, Topics in Statistical Theory, Catchup workshop on statistics